CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

testing-ci

Decide what to run locally before pushing Meshtastic-Android, and read the CI pipeline. Use this whenever you finish a change and need the right verification for its change type, when a CI job fails or is skipped, or when you need to know why the merge queue behaved the way it did.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.skills/testing-ci/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is exceptionally actionable and dense with genuinely non-obvious project knowledge, with a workable verification workflow and an explicit validation step in the riskiest procedure. Its weaknesses are monolithic structure — a large CI-reference dump inlined in SKILL.md with no bundle files — and several passages verbose enough that they could be tightened or split out.

Suggestions

Move the CI architecture catalog (section 4), Runner Strategy, CI Gradle Properties, and CI Conventions into one or two reference files (e.g. references/ci-pipeline.md, references/ci-conventions.md), keeping SKILL.md to local verification guidance plus a brief CI map with clearly signaled links.

Tighten the protobufs-bump/scheduled-updates paragraph and the Cache writes bullet to the decision-relevant facts (when each runs and what the reader must do), cutting the internal mechanics that a reader cannot act on.

Add an explicit final validation checkpoint to the change-type matrix (e.g. 'confirm the tasks you ran match the CI shard that will run them, with -PwarningsAsErrors=true') so every workflow ends in a verify step like the detekt baseline procedure does.

DimensionReasoningScore

Conciseness

Nearly every sentence carries non-inferable project knowledge (detekt baseline task semantics, 'test allTests' ambiguity, layoutlib host-determinism), but long exhaustive passages — the protobufs-bump paragraph, cache-write rules, and the four-tier runner strategy — could be meaningfully tightened or trimmed, fitting 'mostly efficient but could be tightened' rather than 'minor instances'.

3 / 5

Actionability

The body is dominated by copy-paste-ready commands ('./gradlew spotlessApply spotlessCheck detekt detektTypeResolved assembleDebug test allTests', adb pm-grant/am-start lines, exact task paths and flags) plus a concrete change-type verification matrix, fully matching the 'copy-paste ready' anchor.

5 / 5

Workflow Clarity

There is a clear sequence (baseline invocation, change-type matrix, flavor/screenshot checks) and the baseline-regeneration procedure ends with an explicit confirm step ('confirm with detekt detektTypeResolved'), but other workflows (e.g., the change-type matrix) lack a final verification checkpoint, fitting 'clear sequence with most checkpoints; minor validation gaps'.

4 / 5

Progressive Disclosure

Sections are well-headed and repo-file pointers (scripts/verify-rb.sh, .github/instructions/ci-workflows.instructions.md) are clearly signaled one level deep, but no bundle exists and roughly two-thirds of the ~160 lines (CI job catalog, runner tiers, CI conventions, cache rules) is inline reference material that belongs in separate reference files, matching 'content that should be separate is inline'.

3 / 5

Total

15

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that explicitly covers both what the skill does and multiple concrete 'use when' triggers, anchored to a specific project. The only weakness is that the 'what' stays at the level of two general actions without naming the specific verification capabilities the body actually delivers.

DimensionReasoningScore

Specificity

Names the domain ('what to run locally before pushing Meshtastic-Android', 'read the CI pipeline') with two concrete actions, but does not enumerate the specific verifications it covers (detekt, test matrices, flavor checks), matching the 'domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.

3 / 5

Completeness

Both what ('Decide what to run locally before pushing', 'read the CI pipeline') and when are explicitly answered with concrete trigger phrases ('Use this whenever you finish a change and need the right verification for its change type, when a CI job fails or is skipped...'), matching the top anchor. Not 4 because the 'when' is already fully explicit and multi-trigger, not merely adequate.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are present ('finish a change', 'when a CI job fails or is skipped', 'why the merge queue behaved the way it did'), though common variants like 'build failed', 'tests', or 'pipeline' are missing, fitting the 'good keyword coverage; a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a named project ('Meshtastic-Android') with distinct triggers (merge queue behavior, CI job failures), giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 9 missing

Warning

Total

15

/

16

Passed

Repository

meshtastic/Meshtastic-Android

Path

.skills/testing-ci/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.